© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26918
    Prev
    Next
    INDEX
    Explanations

    groupings, sets, composite structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tvrd
    -0.89
    urls
    -0.85
     variety
    -0.84
     įva
    -0.82
    wikia
    -0.79
    ukų
    -0.76
    ictionary
    -0.75
     bite
    -0.75
    variety
    -0.75
     dá
    -0.73
    POSITIVE LOGITS
    組
    0.92
     composite
    0.90
     comples
    0.84
     assemblages
    0.83
     bando
    0.83
    assembled
    0.80
     clumps
    0.79
     himo
    0.79
     paket
    0.79
     női
    0.78
    Activations Density 0.160%

    No Known Activations